Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network

Harold Mouchère 1 Eric Anquetil 1
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : Different problems of generalization of outlier rejection exist depending of the context. In this study we firstly define three different problems depending of the outlier availability during the learning phase of the classifier. Then we propose different solutions to reject outliers with two main strategies: add a rejection class to the classifier or delimit its knowledge to better reject what it has not learned. These solutions are compared with ROC curves to recognize handwritten digits and reject handwritten characters. We show that delimiting knowledge of the classifier is important and that using only a partial subset of outliers do not perform a good reject option.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00104310
Contributor : Anne Jaigu <>
Submitted on : Friday, October 6, 2006 - 11:48:08 AM
Last modification on : Thursday, February 7, 2019 - 2:36:21 PM
Long-term archiving on : Tuesday, April 6, 2010 - 6:46:08 PM

Identifiers

  • HAL Id : inria-00104310, version 1

Citation

Harold Mouchère, Eric Anquetil. Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00104310⟩

Share

Metrics

Record views

189

Files downloads

141